r2_config_manager

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the disclosure burden. It explains that the tool manages Radare2 eval variables, lists useful config keys, and includes operational rules such as not fabricating file paths or command results and closing the session_id when done. It does not disclose side effects of 'set' (e.g., persistence or impact on the session/analysis state) or what get/list return, leaving some behavioral gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is sectioned and the config-key reference is practical and useful. However, it is verbose and somewhat repetitive: the broad opening 'Use when' list overlaps with the later trigger scenario, and the 'must prioritize' sentence adds noise rather than selection value. It could be tightened without losing the valuable config guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description provides substantial config-key context and usage rules, which is helpful for correct invocation. But with no output schema, it does not explain what get/list return, and it does not mention how session_id should be obtained (e.g., from r2_open_file) or whether a target file must already be loaded. These are meaningful gaps for a tool that depends on an active r2 session.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already describes all parameters with 100% coverage, so the baseline is 3. The description adds real value by enumerating concrete config keys ('anal.strings', 'anal.bb.maxsize', 'anal.in' modes) and value examples, which helps an agent choose meaningful key/value pairs beyond the generic schema descriptions. Value format is only illustrated by example, not fully formalized.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies a specific resource (Radare2 analysis/display eval variables) and action (manage via get/set/list), and provides concrete triggers like poor analysis results or function truncation. This distinguishes it from sibling r2 tools. However, the opening 'Binary/reverse-engineering tool. Use when: disassembly, radare2, debugging...' is overly broad for a config manager and slightly dilutes the purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives concrete use cases: when analysis results are unsatisfactory, when functions are truncated, and for deep analysis/config tuning. It does not explicitly name sibling alternatives or state when not to use this tool. The instruction to 'must prioritize this tool' for any disassembly/reverse-engineering question overstates its role, since siblings like r2_disassemble or r2_analyze_target are more appropriate for those tasks.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.